A Comparative Study Between Artificial Neural Networks and Conventional Classifiers for Predicting Diagnosis of Breast Cancer

In this paper a comparative study between linear classification and non-linear classification is performed for the prediction of diagnosis of breast cancer. The most crucial factor for any cancer patient is the diagnosis, if the cancer is detected early it can drastically increase the estimated life expectancy of the patient after the treatment. We propose an Artificial Neural Network based classifier in comparison with linear machine learning algorithms like Support Vector Machine, Logistic Regression and Random Forest based classifiers. The paper presents the details of implementation and the respective results for all the above mentioned classifiers. The comparative study then showed us that SVM had a better performance in terms of sensitivity but overall ANN performed better than the conventional linear classifiers.